Mixup for Supervision, Semi- and Self-Supervision Learning Toolbox and Benchmark

Related tags

Deep Learningopenmixup
Overview

OpenSelfSup

News

  • Downstream tasks now support more methods(Mask RCNN-FPN, RetinaNet, Keypoints RCNN) and more datasets(Cityscapes).
  • 'GaussianBlur' is replaced from Opencv to PIL, and MoCo v2 training speed doubles!
    (time/iter 0.35s-->0.16s, SimCLR and BYOL are also affected.)
  • OpenSelfSup now supports Mixed Precision Training (apex AMP)!
  • A bug of MoCo v2 has been fixed and now the results are reproducible.
  • OpenSelfSup now supports BYOL!

Introduction

The master branch works with PyTorch 1.1 or higher.

OpenSelfSup is an open source unsupervised representation learning toolbox based on PyTorch.

What does this repo do?

Below is the relations among Unsupervised Learning, Self-Supervised Learning and Representation Learning. This repo focuses on the shadow area, i.e., Unsupervised Representation Learning. Self-Supervised Representation Learning is the major branch of it. Since in many cases we do not distingush between Self-Supervised Representation Learning and Unsupervised Representation Learning strictly, we still name this repo as OpenSelfSup.

Major features

  • All methods in one repository

    For comprehensive comparison in all benchmarks, refer to MODEL_ZOO.md. Most of the selfsup pretraining methods are under the batch_size=256, epochs=200 setting.

    Method VOC07 SVM (best layer) ImageNet (best layer)
    ImageNet 87.17 76.17
    Random 30.54 16.21
    Relative-Loc 64.78 49.31
    Rotation-Pred 67.38 54.99
    DeepCluster 74.26 57.71
    NPID 74.50 56.61
    ODC 78.42 57.70
    MoCo 79.18 60.60
    MoCo v2 84.26 67.69
    SimCLR 78.95 61.57
    BYOL (epoch=300) 86.58 72.35

    • Flexibility & Extensibility

      OpenSelfSup follows a similar code architecture of MMDetection while is even more flexible than MMDetection, since OpenSelfSup integrates various self-supervised tasks including classification, joint clustering and feature learning, contrastive learning, tasks with a memory bank, etc.

      For existing methods in this repo, you only need to modify config files to adjust hyper-parameters. It is also simple to design your own methods, please refer to GETTING_STARTED.md.

    • Efficiency

      All methods support multi-machine multi-gpu distributed training.

    • Standardized Benchmarks

      We standardize the benchmarks including logistic regression, SVM / Low-shot SVM from linearly probed features, semi-supervised classification, and object detection. Below are the setting of these benchmarks.

      Benchmarks Setting Remarks
      ImageNet Linear Classification (Multi) goyal2019scaling Evaluate different layers.
      ImageNet Linear Classification (Last) MoCo Evaluate the last layer after global pooling.
      Places205 Linear Classification goyal2019scaling Evaluate different layers.
      ImageNet Semi-Sup Classification
      PASCAL VOC07 SVM goyal2019scaling Costs="1.0,10.0,100.0" to save evaluation time w/o change of results.
      PASCAL VOC07 Low-shot SVM goyal2019scaling Costs="1.0,10.0,100.0" to save evaluation time w/o change of results.
      PASCAL VOC07+12 Object Detection MoCo
      COCO17 Object Detection MoCo

    Change Log

    Please refer to CHANGELOG.md for details and release history.

    [2020-10-14] OpenSelfSup v0.3.0 is released with some bugs fixed and support of new features.

    [2020-06-26] OpenSelfSup v0.2.0 is released with benchmark results and support of new features.

    [2020-06-16] OpenSelfSup v0.1.0 is released.

    Installation

    Please refer to INSTALL.md for installation and dataset preparation.

    Get Started

    Please see GETTING_STARTED.md for the basic usage of OpenSelfSup.

    Benchmark and Model Zoo

    Please refer to MODEL_ZOO.md for for a comprehensive set of pre-trained models and benchmarks.

    License

    This project is released under the Apache 2.0 license.

    Acknowledgement

    • This repo borrows the architecture design and part of the code from MMDetection.
    • The implementation of MoCo and the detection benchmark borrow the code from moco.
    • The SVM benchmark borrows the code from fair_self_supervision_benchmark.
    • openselfsup/third_party/clustering.py is borrowed from deepcluster.

    Contributors

    We encourage researchers interested in Self-Supervised Learning to contribute to OpenSelfSup. Your contributions, including implementing or transferring new methods to OpenSelfSup, performing experiments, reproducing of results, parameter studies, etc, will be recorded in MODEL_ZOO.md. For now, the contributors include: Xiaohang Zhan (@XiaohangZhan), Jiahao Xie (@Jiahao000), Enze Xie (@xieenze), Xiangxiang Chu (@cxxgtxy), Zijian He (@scnuhealthy).

    Contact

    This repo is currently maintained by Xiaohang Zhan (@XiaohangZhan), Jiahao Xie (@Jiahao000) and Enze Xie (@xieenze).

Comments
  • [Feature] Can we load ImageNet data using LMDB?

    [Feature] Can we load ImageNet data using LMDB?

    Describe the feature

    Current ImageNet data loader can only support pillow, cv2 backends to load images. By some reasone, I need to use LMDB to load dataset which is supported by mmcls. https://github.com/Westlake-AI/openmixup/blob/8966870a05b85ea940a02c4646693ec101ab0575/openmixup/datasets/data_sources/image_list.py#L49-L51

    enhancement 
    opened by wang-tf 4
  • Question about the invTrans in the visualization code for automix

    Question about the invTrans in the visualization code for automix

    Hi, thank you for your great work. I found that the invTrans in the visualization code for automix use cifar dataset's mean & std by default. Will it work when i input the imagenet images?

    https://github.com/Westlake-AI/openmixup/blob/90dab92464e94ac5c4139c37f07ed21df9c2affb/openmixup/models/classifiers/automix_V1plus.py#L353

    help wanted 
    opened by mrbulb 4
  • How to convert model output to torchscript file?

    How to convert model output to torchscript file?

    Checklist

    • I have searched related issues but cannot get the expected help.
    • I have read related documents and don't know what to do.

    Describe the question you meet

    I already using config modified from MogaNet to train the perfect model, but I need to convert it to torchscript. How to convert the .pth to torchscript(.pt), I try the general method but get error, because the .pth file only contains the weight, and not contains the model.

    如何能转换模型文件到 TorchScript 格式？ 我已经使用修改的 MogaNet 配置文件训练出了一个良好的模型，但是我需要转换 .pth 文件到 .pt 文件，即 TorchScript 格式。 如何转换模型输出文件 .pth 到 TorchScript？我尝试了一些通用方法，但是不能成功，因为 .pth 文件仅仅包含权重，并不包含模型网络。

    help wanted 
    opened by nikbobo 3
  • Where will I get the pretrained code for moganet?

    Where will I get the pretrained code for moganet?

    Checklist

    • I have searched related issues but cannot get the expected help.
    • I have read related documents and don't know what to do.

    Describe the question you meet

    [here]

    Post related information

    1. The output of pip list | grep "mmcv\|mmcls\|^torch" [here]
    2. Your config file if you modified it or created a new one.
    [here]
    1. Your train log file if you meet the problem during training. [here]
    2. Other code you modified in the mmcls folder. [here]
    help wanted 
    opened by M-SunRise 3
  • there is a problem when i run :python setup.py develop

    there is a problem when i run :python setup.py develop

    when i run:python setup.py develop,there is a problem,i paste it down here

    running develop
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\easy_install.py:144: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards
-based tools.
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tool
s.
  warnings.warn(
running egg_info
writing openmixup.egg-info\PKG-INFO
writing dependency_links to openmixup.egg-info\dependency_links.txt
writing requirements to openmixup.egg-info\requires.txt
writing top-level names to openmixup.egg-info\top_level.txt
reading manifest file 'openmixup.egg-info\SOURCES.txt'
adding license file 'LICENSE'
writing manifest file 'openmixup.egg-info\SOURCES.txt'
running build_ext
Creating c:\users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\openmixup.egg-link (link to .)
openmixup 0.2.5+90dab92 is already the active version in easy-install.pth

Installed d:\python_projects\openmixup
Processing dependencies for openmixup==0.2.5+90dab92
Searching for faiss-gpu==1.6.1
Reading https://pypi.org/simple/faiss-gpu/
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.5.3 is an invalid version and will not be supported in a future release
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning:  is an invalid version and will not be supported in a future release
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.6.0 is an invalid version and will not be supported in a future release
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.6.1 is an invalid version and will not be supported in a future release
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.6.3 is an invalid version and will not be supported in a future release
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.6.4 is an invalid version and will not be supported in a future release
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.6.4.post2 is an invalid version and will not be supported in a future relea
se
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.6.5 is an invalid version and will not be supported in a future release
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.7.0 is an invalid version and will not be supported in a future release
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.7.1 is an invalid version and will not be supported in a future release
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.7.1.post1 is an invalid version and will not be supported in a future relea
se
  warnings.warn(
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py:123: PkgResourcesDeprecationWarning: gpu-1.7.1.post2 is an invalid version and will not be supported in a future relea
se
  warnings.warn(
Downloading https://files.pythonhosted.org/packages/1d/d4/290ed049631dc061843920cd6e2b5d9af25cb5c98cb7ecbe2b7ca4bebf12/faiss-gpu-1.6.1.tar.gz#sha256=7a280e951d305d654a116b9f31275169f30841c8b851f0d689421ef8a
3ecf7b8
Best match: faiss-gpu 1.6.1
Processing faiss-gpu-1.6.1.tar.gz
Writing C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\setup.cfg
Running faiss-gpu-1.6.1\setup.py -q bdist_egg --dist-dir C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\egg-dist-tmp-snlcnz4n
C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tool
s.
  warnings.warn(
Traceback (most recent call last):
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 156, in save_modules
    yield saved
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 198, in setup_context
    yield
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 259, in run_setup
    _execfile(setup_script, ns)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 46, in _execfile
    exec(code, globals, locals)
  File "C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\setup.py", line 91, in <module>

  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\__init__.py", line 87, in setup
    return distutils.core.setup(**attrs)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\core.py", line 185, in setup
    return run_commands(dist)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\core.py", line 201, in run_commands
    dist.run_commands()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 973, in run_commands
    self.run_command(cmd)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\dist.py", line 1217, in run_command
    super().run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 992, in run_command
    cmd_obj.run()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\bdist_egg.py", line 165, in run
    cmd = self.call_command('install_lib', warn_dir=0)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\bdist_egg.py", line 151, in call_command
    self.run_command(cmdname)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\cmd.py", line 319, in run_command
    self.distribution.run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\dist.py", line 1217, in run_command
    super().run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 992, in run_command
    cmd_obj.run()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\install_lib.py", line 11, in run
    self.build()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\command\install_lib.py", line 112, in build
    self.run_command('build_ext')
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\cmd.py", line 319, in run_command
    self.distribution.run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\dist.py", line 1217, in run_command
    super().run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 992, in run_command
    cmd_obj.run()
  File "C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\setup.py", line 45, in run
    sha = out.strip().decode('ascii')
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 346, in run
    self.build_extensions()
  File "C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\setup.py", line 50, in build_extensions

  File "C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\setup.py", line 58, in _remove_flag
    sha = __version__.split('+')[-1]
AttributeError: 'MSVCCompiler' object has no attribute 'compiler'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "setup.py", line 168, in <module>
    setup(
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\__init__.py", line 87, in setup
    return distutils.core.setup(**attrs)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\core.py", line 185, in setup
    return run_commands(dist)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\core.py", line 201, in run_commands
    dist.run_commands()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 973, in run_commands
    self.run_command(cmd)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\dist.py", line 1217, in run_command
    super().run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 992, in run_command
    cmd_obj.run()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\develop.py", line 34, in run
    self.install_for_development()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\develop.py", line 129, in install_for_development
    self.process_distribution(None, self.dist, not self.no_deps)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\easy_install.py", line 754, in process_distribution
    distros = WorkingSet([]).resolve(
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py", line 789, in resolve
    dist = best[req.key] = env.best_match(
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py", line 1075, in best_match
    return self.obtain(req, installer)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\pkg_resources\__init__.py", line 1087, in obtain
    return installer(requirement)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\easy_install.py", line 681, in easy_install
    return self.install_item(spec, dist.location, tmpdir, deps)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\easy_install.py", line 707, in install_item
    dists = self.install_eggs(spec, download, tmpdir)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\easy_install.py", line 900, in install_eggs
    return self.build_and_install(setup_script, setup_base)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\easy_install.py", line 1174, in build_and_install
    self.run_setup(setup_script, setup_base, args)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\easy_install.py", line 1158, in run_setup
    run_setup(setup_script, args)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 262, in run_setup
    raise
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\contextlib.py", line 131, in __exit__
    self.gen.throw(type, value, traceback)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 198, in setup_context
    yield
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\contextlib.py", line 131, in __exit__
    self.gen.throw(type, value, traceback)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 169, in save_modules
    saved_exc.resume()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 143, in resume
    raise exc.with_traceback(self._tb)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 156, in save_modules
    yield saved
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 198, in setup_context
    yield
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 259, in run_setup
    _execfile(setup_script, ns)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\sandbox.py", line 46, in _execfile
    exec(code, globals, locals)
  File "C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\setup.py", line 91, in <module>

  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\__init__.py", line 87, in setup
    return distutils.core.setup(**attrs)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\core.py", line 185, in setup
    return run_commands(dist)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\core.py", line 201, in run_commands
    dist.run_commands()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 973, in run_commands
    self.run_command(cmd)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\dist.py", line 1217, in run_command
    super().run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 992, in run_command
    cmd_obj.run()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\bdist_egg.py", line 165, in run
    cmd = self.call_command('install_lib', warn_dir=0)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\bdist_egg.py", line 151, in call_command
    self.run_command(cmdname)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\cmd.py", line 319, in run_command
    self.distribution.run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\dist.py", line 1217, in run_command
    super().run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 992, in run_command
    cmd_obj.run()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\command\install_lib.py", line 11, in run
    self.build()
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\command\install_lib.py", line 112, in build
    self.run_command('build_ext')
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\cmd.py", line 319, in run_command
    self.distribution.run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\dist.py", line 1217, in run_command
    super().run_command(command)
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\dist.py", line 992, in run_command
    cmd_obj.run()
  File "C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\setup.py", line 45, in run
    sha = out.strip().decode('ascii')
  File "C:\Users\shaoshuai\anaconda3\envs\openmixup\lib\site-packages\setuptools\_distutils\command\build_ext.py", line 346, in run
    self.build_extensions()
  File "C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\setup.py", line 50, in build_extensions

  File "C:\Users\SHAOSH~1\AppData\Local\Temp\easy_install-3zs3m1q3\faiss-gpu-1.6.1\setup.py", line 58, in _remove_flag
    sha = __version__.split('+')[-1]
AttributeError: 'MSVCCompiler' object has no attribute 'compiler'

    It looks like can't install faiss.I try to install faiss through pip command,but don't work. Please help me.

    help wanted 
    opened by 774911840 3
  • Where can we find the Resnet fine-tuning config file for A2MIM?

    Where can we find the Resnet fine-tuning config file for A2MIM?

    Checklist

    • I have searched related issues but cannot get the expected help.
    • I have read related documents and don't know what to do.

    Describe the question you meet

    In this page, I can not find the Fine-tuning Config for ResNet-50. There is a likely config(configs/benchmarks/classification/imagenet/r50_rsb_a2_ft_sz224_8xb256_cos_fp16_ep100.py) in the directory. Is it the right cofnig file?

    help wanted 
    opened by wang-tf 2
  • Update New Features and Update Documents in V0.2.6

    Update New Features and Update Documents in V0.2.6

    Updating features:

    1. Support new self-supervised method BEiT with ViT-Base on ImageNet-1K, and fix bugs of CAE, MaskFeat, and SimMIM in Dataset, Model, and Head. Note that we added HOG feature implementation borrowed from the original repo for MaskFeat.
    2. Support new backbone architecture DeiT-3 and provide configs.
    3. Update pre-training and fine-tuning config files, and documents for the relevant masked image modeling (MIM) methods (BEiT, MaskFeat, CAE, and A2MIM).
    4. Support Grad-CAM visualization tools vis_cam.py of supported architectures.

    Updating documents:

    1. Update the template and add the latest paper lists of mixup and MIM methods in Awesome Mixups and Awesome MIM.
    2. Update documents of tools.
    bug documentation enhancement 
    opened by Lupin1998 2
  • SAMix Configs for TinyImageNet

    SAMix Configs for TinyImageNet

    Hey, would it be possible to get SAMix Resnet 18 config files for TinyImageNet? I'm trying to adapt the CIFAR-100 config to Tiny but I'm running into shape mismatch issues. Thank you.

    update 
    opened by aswathn1 2
  • No module named 'openmixup'

    No module named 'openmixup'

    Hi authors, Thanks for your great work. When I run the script following your GETTING_STARTED.md, it returns me "no module named ''openmixup". When I tried to import openmixup in python directly, it tells me "no module named 'openmixup.version'". It seems that the version.py file in in the .gitignore list. Is this the reason for the error?

    bug 
    opened by xiangyu8 2
  • Refactoring and Support New Methods and Documents (V0.2.7)

    Refactoring and Support New Methods and Documents (V0.2.7)

    Code refactoring:

    1. Refactor openmixup.core (instead of openmixup.hooks) and openmixup.models.augments (contains mixup augmentation methods which are originally implemented in openmixup.models.utils). After code refactoring, the macro design of OpenMixup is similar to most projects of MMLab.
    2. Support deployment of ONNX and TorchScript in openmixup.core.export and tools/deployment. We refactored the abstract class BaseModel (implemented in openmixup/models/classifiers/base_model.py) to support forward_inference (for custom inference and visualization). We also refactored openmixup.models.heads and openmixup.models.losses to support forward_inference. You can deploy the classification models in OpenMixup according to deployment tutorials.
    3. Support testing API methods in openmixup/apis/test.py for evaluation and deployment of classification models.
    4. Refactor openmixup.core.optimizers to separate optimizers and builders and support the latest Adan optimizer.

    Supporting new features:

    1. Support detailed usage instructions in README of config files for image classification methods in configs/classification, e.g., mixups on ImageNet. We will update READMEs of other methods in configs/selfsup and configs/semisup in a few weeks.
    2. Refine the origianzation of README files according to README-Template.
    3. Support the new mixup augmentation method (AlignMix) and provide the relevant config files in various datasets.

    Updating documents:

    1. Update documents of mixup benchmarks on ImageNet in Model_Zoo_sup.md. Update config files for supported mixup methods.
    2. Update formats (figures, introductions and content tables) of awesome lists in Awesome Mixups and Awesome MIM and provide the latest methods.
    enhancement update Refactoring 
    opened by Lupin1998 1
  • Release Models of MogaNet and Update Features in V0.2.6

    Release Models of MogaNet and Update Features in V0.2.6

    Updateing new features:

    1. Fix the classification heads and update implementations and config files of AlexNet and InceptionV3.

    Uploading Benchmark Results (release):

    1. Updating mixup benchmarks on ImageNet as provided in AutoMix and update results in Model_Zoo_sup.md.
    2. Release pre-trained models and logs of MogaNet.

    Updating documents:

    1. Update documents of mixup benchmarks on ImageNet with new backbones in Model_Zoo_sup.md.
    2. Update awesome lists in Awesome Mixups and Awesome MIM and provide teaser figures of most papers as illustrations.
    documentation enhancement update 
    opened by Lupin1998 1
  • [Feature] Migration to OpenMMLab 2.0 framework.

    [Feature] Migration to OpenMMLab 2.0 framework.

    Describe the feature

    Hi, OpenMixup Team.

    We have release the OpenMMLab 2.0 framework, and release the new version of MMClassification and MMSelfSup.

    We also introduce the new features in these two blogs.

    • https://zhuanlan.zhihu.com/p/574842341
    • https://zhuanlan.zhihu.com/p/573317958

    If you think the new features are useful to your project, feel free to try or migrate to OpenMMLab 2.0 framework.

    MMClassification/MMSelfSup Team.

    enhancement 
    opened by tonysy 1
  • AutoMix tutorial that is independent of MMClassification

    AutoMix tutorial that is independent of MMClassification

    Dear Authors,

    Inspiring work! Could you please provide a simplified demo/tutorial of how to use AutoMix in general PyTorch training? I have no experience of using OpenMMLab-style framework. A small demo like google colab notebook would be of great help!

    Thanks!

    help wanted 
    opened by lofrienger 1
Releases(moganet-in1k-weights)
Owner
AI Lab, Westlake University
AI Lab, Westlake University
GitHub Repository
Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation)

Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation) Download Synthia dataset The model uses

32 Sep 21, 2022
UniLM AI - Large-scale Self-supervised Pre-training across Tasks, Languages, and Modalities

Pre-trained (foundation) models across tasks (understanding, generation and translation), languages (100+ languages), and modalities (language, image, audio, vision + language, audio + language, etc.

Microsoft 7.6k Jan 01, 2023
Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation

OSCAR Project Page | Paper This repository contains the codebase used in OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Ma

NVIDIA Research Projects 74 Dec 22, 2022
Code release of paper "Deep Multi-View Stereo gone wild"

Deep MVS gone wild Pytorch implementation of "Deep MVS gone wild" (Paper | website) This repository provides the code to reproduce the experiments of

François Darmon 53 Dec 24, 2022
This repository contains python code necessary to replicated the experiments performed in our paper "Invariant Ancestry Search"

InvariantAncestrySearch This repository contains python code necessary to replicated the experiments performed in our paper "Invariant Ancestry Search

Phillip Bredahl Mogensen 0 Feb 02, 2022
Astrostatistics class for the MSc degree in Astrophysics at the University of Milan-Bicocca (Italy)

Astrostatistics Davide Gerosa - [email protected] University of Mil

Davide Gerosa 25 Jan 02, 2023
Provided is code that demonstrates the training and evaluation of the work presented in the paper: "On the Detection of Digital Face Manipulation" published in CVPR 2020.

FFD Source Code Provided is code that demonstrates the training and evaluation of the work presented in the paper: "On the Detection of Digital Face M

88 Nov 22, 2022
[CVPR 2020] Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation

Contents Local and Global GAN Cross-View Image Translation Semantic Image Synthesis Acknowledgments Related Projects Citation Contributions Collaborat

Hao Tang 131 Dec 07, 2022
Improving Compound Activity Classification via Deep Transfer and Representation Learning

Improving Compound Activity Classification via Deep Transfer and Representation Learning This repository is the official implementation of Improving C

NingLab 2 Nov 24, 2021
True per-item rarity for Loot

True-Rarity True per-item rarity for Loot (For Adventurers) and More Loot A.K.A mLoot each out/true_rarity_{item_type}.json file contains probabilitie

Dan R. 3 Jul 26, 2022
A Pytorch Implementation of Source Data-free Domain Adaptation for a Faster R-CNN

A Pytorch Implementation of Source Data-free Domain Adaptation for a Faster R-CNN Please follow Faster R-CNN and DAF to complete the environment confi

2 Jan 12, 2022
“英特尔创新大师杯”深度学习挑战赛 赛道3：CCKS2021中文NLP地址相关性任务

基于 bert4keras 的一个baseline 不作任何 数据trick 单模 线上 最高可到 0.7891 # 基础 版 train.py 0.7769 # transformer 各层 cls concat 明神的trick https://xv44586.git

孙永松 7 Dec 28, 2021
Repository for RNNs using TensorFlow and Keras - LSTM and GRU Implementation from Scratch - Simple Classification and Regression Problem using RNNs

RNN 01- RNN_Classification Simple RNN training for classification task of 3 signal: Sine, Square, Triangle. 02- RNN_Regression Simple RNN training for

Nahid Ebrahimian 13 Dec 13, 2022
HashNeRF-pytorch - Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives

HashNeRF-pytorch Instant-NGP recently introduced a Multi-resolution Hash Encodin

Yash Sanjay Bhalgat 616 Jan 06, 2023
My coursework for Machine Learning (2021 Spring) at National Taiwan University (NTU)

Machine Learning 2021 Machine Learning (NTU EE 5184, Spring 2021) Instructor: Hung-yi Lee Course Website : (https://speech.ee.ntu.edu.tw/~hylee/ml/202

100 Dec 26, 2022
[AAAI-2022] Official implementations of MCL: Mutual Contrastive Learning for Visual Representation Learning

Mutual Contrastive Learning for Visual Representation Learning This project provides source code for our Mutual Contrastive Learning for Visual Repres

winycg 48 Jan 02, 2023
CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification (ICCV2021)

CM-NAS Official Pytorch code of paper CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification in ICCV2021. Vis

JDAI-CV 40 Nov 25, 2022
《Rethinking Sptil Dimensions of Vision Trnsformers》(2021)

Rethinking Spatial Dimensions of Vision Transformers Byeongho Heo, Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Junsuk Choe, Seong Joon Oh | Paper NAVER

NAVER AI 224 Dec 27, 2022
A scikit-learn-compatible module for estimating prediction intervals.

MAPIE - Model Agnostic Prediction Interval Estimator MAPIE allows you to easily estimate prediction intervals (or prediction sets) using your favourit

588 Jan 04, 2023
Pytorch implementation for the Temporal and Object Quantification Networks (TOQ-Nets).

TOQ-Nets-PyTorch-Release Pytorch implementation for the Temporal and Object Quantification Networks (TOQ-Nets). Temporal and Object Quantification Net

Zhezheng Luo 9 Jun 30, 2022